Research on judgment reasoning using natural language inference in Chinese medical texts

Abstract

Machine reading comprehension (MRC) is a task used to test the degree to which a machine understands natural language by asking the machine to answer questions according to a given context. Judgment reasoning is one of MRC tasks which means that given a context and questions, let machine gives the true and false answers, for some real-world data, there will be another option of unknown. Considering the current research status, this paper uses natural language inference (NLI) models to further study this judgment reasoning task, which is mainly to judge the semantic relationship between two sentences. In our paper, we first explain how the NLI task can be used to train universal sentence encoding models in the judgment reasoning process and subsequently describe the architectures used in NLI task, which covers a suitable range of sentence encoders currently in use and take the bi-directional long short-term memory (BI-LSTM) model with max-pooling over the hidden representations as an example explained in this paper. After some comparative experiments, we have verified that our NLI models are effective strategies to improve the performance of judgment reasoning in Chinese medical texts, which can effectively improve the accuracy values.